Blind separation of rotating machine sources: Bilinear forms and convolutive mixtures

Alexander Ypma; Amir Leshem; Robert P.W. Duin

doi:10.1016/s0925-2312(02)00524-6

Blind separation of rotating machine sources: Bilinear forms and convolutive mixtures

Alexander Ypma, Amir Leshem, Robert P.W. Duin

Research output: Contribution to journal › Article › peer-review

77 Scopus citations

Abstract

We propose the use of blind source separation (BSS) for separation of a machine signature from distorted measurements. Based on an analysis of the mixing processes relevant for machine source separation, we indicate that instantaneous mixing may hold in acoustic monitoring. We then present a bilinear forms-based approach to instantaneous source separation. For simulated acoustic mixing, we show that this method may give rise to a more robust separation. For vibrational monitoring, a convolutive mixture model is more appropriate. The demixing algorithm by Nguyen Thi-Jutten allows for separation of the contributions of two coupled machines, both in an experimental setup and in a real-world situation. We conclude that BSS is a feasible approach for blind separation of distorted rotating machine sources.

Original language	English
Pages (from-to)	349-368
Number of pages	20
Journal	Neurocomputing
Volume	49
Issue number	1-4
DOIs	https://doi.org/10.1016/s0925-2312(02)00524-6
State	Published - Dec 2002
Externally published	Yes

Bibliographical note

Funding Information:
This work is partially supported by the Dutch Technology Foundation STW, Project No. DTN-44.3584 “Machine diagnostics by neural networks”, by TNO-TPD b.v. (Delft) and the Dutch Ministry of Housing, Spatial planning and Environment (Depart. of VROM). We like to thank Ronald Ligteringen (TU Delft), TechnoFysica b.v. (Barendrecht) and Landustrie b.v. (Sneek) for assistance with measurements, and Willem Keijzer (RND Mechanical Engineering b.v. Delft) and Guillaume Gelle (Reims University, France) for fruitful discussions. Moreover, we thank the anonymous reviewers for many useful remarks.

Funding

This work is partially supported by the Dutch Technology Foundation STW, Project No. DTN-44.3584 “Machine diagnostics by neural networks”, by TNO-TPD b.v. (Delft) and the Dutch Ministry of Housing, Spatial planning and Environment (Depart. of VROM). We like to thank Ronald Ligteringen (TU Delft), TechnoFysica b.v. (Barendrecht) and Landustrie b.v. (Sneek) for assistance with measurements, and Willem Keijzer (RND Mechanical Engineering b.v. Delft) and Guillaume Gelle (Reims University, France) for fruitful discussions. Moreover, we thank the anonymous reviewers for many useful remarks.

Funders	Funder number
Dutch Ministry of Housing, Spatial planning and Environment
Stichting voor de Technische Wetenschappen	DTN-44.3584

Keywords

Bilinear forms
Blind source separation
Condition monitoring
Convolutive mixture
Machine vibration

Access to Document

10.1016/s0925-2312(02)00524-6

Cite this

@article{50dad0aaed994843a6302ae9244537e6,

title = "Blind separation of rotating machine sources: Bilinear forms and convolutive mixtures",

abstract = "We propose the use of blind source separation (BSS) for separation of a machine signature from distorted measurements. Based on an analysis of the mixing processes relevant for machine source separation, we indicate that instantaneous mixing may hold in acoustic monitoring. We then present a bilinear forms-based approach to instantaneous source separation. For simulated acoustic mixing, we show that this method may give rise to a more robust separation. For vibrational monitoring, a convolutive mixture model is more appropriate. The demixing algorithm by Nguyen Thi-Jutten allows for separation of the contributions of two coupled machines, both in an experimental setup and in a real-world situation. We conclude that BSS is a feasible approach for blind separation of distorted rotating machine sources.",

keywords = "Bilinear forms, Blind source separation, Condition monitoring, Convolutive mixture, Machine vibration",

author = "Alexander Ypma and Amir Leshem and Duin, {Robert P.W.}",

note = "Funding Information: This work is partially supported by the Dutch Technology Foundation STW, Project No. DTN-44.3584 “Machine diagnostics by neural networks”, by TNO-TPD b.v. (Delft) and the Dutch Ministry of Housing, Spatial planning and Environment (Depart. of VROM). We like to thank Ronald Ligteringen (TU Delft), TechnoFysica b.v. (Barendrecht) and Landustrie b.v. (Sneek) for assistance with measurements, and Willem Keijzer (RND Mechanical Engineering b.v. Delft) and Guillaume Gelle (Reims University, France) for fruitful discussions. Moreover, we thank the anonymous reviewers for many useful remarks. ",

year = "2002",

month = dec,

doi = "10.1016/s0925-2312(02)00524-6",

language = "אנגלית",

volume = "49",

pages = "349--368",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier",

number = "1-4",

}

TY - JOUR

T1 - Blind separation of rotating machine sources

T2 - Bilinear forms and convolutive mixtures

AU - Ypma, Alexander

AU - Leshem, Amir

AU - Duin, Robert P.W.

N1 - Funding Information: This work is partially supported by the Dutch Technology Foundation STW, Project No. DTN-44.3584 “Machine diagnostics by neural networks”, by TNO-TPD b.v. (Delft) and the Dutch Ministry of Housing, Spatial planning and Environment (Depart. of VROM). We like to thank Ronald Ligteringen (TU Delft), TechnoFysica b.v. (Barendrecht) and Landustrie b.v. (Sneek) for assistance with measurements, and Willem Keijzer (RND Mechanical Engineering b.v. Delft) and Guillaume Gelle (Reims University, France) for fruitful discussions. Moreover, we thank the anonymous reviewers for many useful remarks.

PY - 2002/12

Y1 - 2002/12

N2 - We propose the use of blind source separation (BSS) for separation of a machine signature from distorted measurements. Based on an analysis of the mixing processes relevant for machine source separation, we indicate that instantaneous mixing may hold in acoustic monitoring. We then present a bilinear forms-based approach to instantaneous source separation. For simulated acoustic mixing, we show that this method may give rise to a more robust separation. For vibrational monitoring, a convolutive mixture model is more appropriate. The demixing algorithm by Nguyen Thi-Jutten allows for separation of the contributions of two coupled machines, both in an experimental setup and in a real-world situation. We conclude that BSS is a feasible approach for blind separation of distorted rotating machine sources.

AB - We propose the use of blind source separation (BSS) for separation of a machine signature from distorted measurements. Based on an analysis of the mixing processes relevant for machine source separation, we indicate that instantaneous mixing may hold in acoustic monitoring. We then present a bilinear forms-based approach to instantaneous source separation. For simulated acoustic mixing, we show that this method may give rise to a more robust separation. For vibrational monitoring, a convolutive mixture model is more appropriate. The demixing algorithm by Nguyen Thi-Jutten allows for separation of the contributions of two coupled machines, both in an experimental setup and in a real-world situation. We conclude that BSS is a feasible approach for blind separation of distorted rotating machine sources.

KW - Bilinear forms

KW - Blind source separation

KW - Condition monitoring

KW - Convolutive mixture

KW - Machine vibration

UR - http://www.scopus.com/inward/record.url?scp=0346665840&partnerID=8YFLogxK

U2 - 10.1016/s0925-2312(02)00524-6

DO - 10.1016/s0925-2312(02)00524-6

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:0346665840

SN - 0925-2312

VL - 49

SP - 349

EP - 368

JO - Neurocomputing

JF - Neurocomputing

IS - 1-4

ER -

Blind separation of rotating machine sources: Bilinear forms and convolutive mixtures

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this